Exploratory_Data_Analysis

Image("E:\DataScience\Data_Center\T_20_World_cup_data\ICC_Men's_T20_World_Cup_2021.png")

pwd

'E:\\DataScience\\Data_Center\\T_20_World_cup_data'

import os
import matplotlib.pyplot as plt 
import seaborn as sns
sns.set_style('darkgrid')
import plotly.express as px
import pandas as pd
import numpy as np
from scipy import signal

#to supress warning
import warnings
warnings.filterwarnings('ignore')


#to make shell more intractive
from IPython.display import display
from IPython.display import Image

# setting up the chart size and background
plt.rcParams['figure.figsize'] = (16, 8)
plt.style.use('fivethirtyeight')

path ="E:\DataScience\Data_Center\T_20_World_cup_data"
dir_list = os.listdir(path)
print(dir_list)

['.ipynb_checkpoints', 'EDA_T-20WorldCup.ipynb', "ICC_Men's_T20_World_Cup_2021.png", 'kaggle_data.csv']

df =pd.read_csv("E:\DataScience\Data_Center\T_20_World_cup_data\kaggle_data.csv")

df.head()

	Unnamed: 0	team_1	team_2	stage	Winner_toss	Toss_descision	time	venue	avg_temperature	best_bowler	...	best_bowler_country	best_batter	batting_hand	high_indvidual_scores	strike_rate	best_batter_team	target	target_achieved	Player_of_the_match	Winner
0	Match_1	Australia	SouthAfrica	Group_stage	Australia	Fielding	afternoon	Abu_Dhabi	30	Josh_Hazlewood	...	Australia	Aiden_Markram	Right	40	111.10	SouthAfrica	119	1	Josh_Hazlewood	Australia
1	Match_2	England	Windies	Group_stage	England	Fielding	evening	Dubai	33	Adil_Rashid	...	England	Jos_Buttler	Right	24	109.10	England	56	1	Moeen_Ali	England
2	Match_3	Srilanka	Bangladesh	Group_stage	Srilanka	Fielding	afternoon	Sharjah	34	Shakib_al_Hassan	...	Bangladesh	Charith_Asalanka	Left	80	163.20	Srilanka	172	1	Charith_Asalanka	Srilanka
3	Match_4	Pakistan	India	Group_stage	Pakistan	Fielding	evening	Dubai	34	Shaheen_shah	...	Pakistan	Muhammad_Rizwan	Right	79	143.60	Pakistan	152	1	Shaheen_shah	Pakistan
4	Match_5	Afghanistan	Scotland	Group_stage	Afghanistan	Batting	evening	Sharjah	33	Mujeeb_ur_Rehman	...	Afghanistan	Najibullah_Zadran	Left	59	173.53	Afghanistan	191	0	Mujeeb_ur_Rehman	Afghanistan

5 rows × 24 columns

df.tail()

	Unnamed: 0	team_1	team_2	stage	Winner_toss	Toss_descision	time	venue	avg_temperature	best_bowler	...	best_bowler_country	best_batter	batting_hand	high_indvidual_scores	strike_rate	best_batter_team	target	target_achieved	Player_of_the_match	Winner
28	Match_29	Pakistan	ScotLand	Group_stage	Pakistan	Batting	evening	Sharjah	27	Shadab_Khan	...	Pakistan	Babar_Azam	Right	66	140.43	Pakistan	190	0	Shoaib_Malik	Pakistan
29	Match_30	India	Namibia	Group_stage	India	Fielding	evening	Dubai	28	Ravindra_Jadeja	...	India	Rohit_Sharma	Right	56	151.35	India	133	1	Ravindra_Jadeja	India
30	Match_31	New_Zealand	England	Semi_Final	New_Zealand	Fielding	evening	Abu_Dhabi	28	Liam_Livingstone	...	England	Daryl_Mitchell	Right	72	153.19	New_Zealand	167	1	Daryl_Mitchell	New_Zealand
31	Match_32	Australia	Pakistan	Semi_Final	Australia	Fielding	evening	Dubai	29	Shadab_Khan	...	Pakistan	Muhammad_Rizwan	Right	67	128.85	Pakistan	177	1	Matthew_Wade	Australia
32	Match_33	Australia	New_Zealand	Final	Australia	Fielding	evening	Dubai	26	Josh_Hazlewood	...	Australia	Kane_Williamson	Right	85	177.08	New_Zealand	173	1	Mitchell_Marsh	Australia

5 rows × 24 columns

df.columns

Index(['Unnamed: 0', 'team_1', 'team_2', 'stage', 'Winner_toss',
       'Toss_descision', 'time', 'venue', 'avg_temperature', 'best_bowler',
       'bowling_arm', 'bowling_style', 'most_individual_wickets', 'economy',
       'best_bowler_country', 'best_batter', 'batting_hand',
       'high_indvidual_scores', 'strike_rate', 'best_batter_team', 'target',
       'target_achieved', 'Player_of_the_match', 'Winner'],
      dtype='object')

df.describe()

	avg_temperature	most_individual_wickets	economy	high_indvidual_scores	strike_rate	target	target_achieved
count	33.000000	33.000000	33.000000	33.000000	33.000000	33.000000	33.000000
mean	29.272727	2.878788	5.215758	62.393939	152.402121	146.606061	0.696970
std	2.577217	0.892944	2.187966	20.135385	33.999070	37.136521	0.466694
min	20.000000	1.000000	0.900000	24.000000	97.060000	56.000000	0.000000
25%	28.000000	2.000000	4.000000	45.000000	136.360000	125.000000	0.000000
50%	29.000000	3.000000	4.800000	65.000000	153.190000	152.000000	1.000000
75%	30.000000	3.000000	6.250000	79.000000	162.900000	173.000000	1.000000
max	34.000000	5.000000	12.000000	101.000000	263.160000	211.000000	1.000000

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 33 entries, 0 to 32
Data columns (total 24 columns):
 #   Column                   Non-Null Count  Dtype  
---  ------                   --------------  -----  
 0   Unnamed: 0               33 non-null     object 
 1   team_1                   33 non-null     object 
 2   team_2                   33 non-null     object 
 3   stage                    33 non-null     object 
 4   Winner_toss              33 non-null     object 
 5   Toss_descision           33 non-null     object 
 6   time                     33 non-null     object 
 7   venue                    33 non-null     object 
 8   avg_temperature          33 non-null     int64  
 9   best_bowler              33 non-null     object 
 10  bowling_arm              33 non-null     object 
 11  bowling_style            33 non-null     object 
 12  most_individual_wickets  33 non-null     int64  
 13  economy                  33 non-null     float64
 14  best_bowler_country      33 non-null     object 
 15  best_batter              33 non-null     object 
 16  batting_hand             33 non-null     object 
 17  high_indvidual_scores    33 non-null     int64  
 18  strike_rate              33 non-null     float64
 19  best_batter_team         33 non-null     object 
 20  target                   33 non-null     int64  
 21  target_achieved          33 non-null     int64  
 22  Player_of_the_match      33 non-null     object 
 23  Winner                   33 non-null     object 
dtypes: float64(2), int64(5), object(17)
memory usage: 6.3+ KB

df.isnull().sum()

Unnamed: 0                 0
team_1                     0
team_2                     0
stage                      0
Winner_toss                0
Toss_descision             0
time                       0
venue                      0
avg_temperature            0
best_bowler                0
bowling_arm                0
bowling_style              0
most_individual_wickets    0
economy                    0
best_bowler_country        0
best_batter                0
batting_hand               0
high_indvidual_scores      0
strike_rate                0
best_batter_team           0
target                     0
target_achieved            0
Player_of_the_match        0
Winner                     0
dtype: int64

df.nunique(axis=0)

Unnamed: 0                 33
team_1                     10
team_2                     13
stage                       3
Winner_toss                11
Toss_descision              2
time                        2
venue                       3
avg_temperature             9
best_bowler                26
bowling_arm                 2
bowling_style               5
most_individual_wickets     5
economy                    24
best_bowler_country        11
best_batter                23
batting_hand                2
high_indvidual_scores      28
strike_rate                33
best_batter_team           11
target                     27
target_achieved             2
Player_of_the_match        30
Winner                     10
dtype: int64

A=df['team_1'].unique()
print(A)

['Australia' 'England' 'Srilanka' 'Pakistan' 'Afghanistan' 'SouthAfrica'
 'Namibia' 'Windies' 'New_Zealand' 'India']

B =df['stage'].unique()
print(B)

['Group_stage' 'Semi_Final' 'Final']

C=df['Winner_toss'].unique()
print(C)

['Australia' 'England' 'Srilanka' 'Pakistan' 'Afghanistan' 'SouthAfrica'
 'Bangladesh' 'Namibia' 'New_Zealand' 'Windies' 'India']

D=df['Toss_descision'].unique()
print(D)

['Fielding' 'Batting']

E=df['time'].unique()
print(E)

['afternoon' 'evening']

F =df['venue'].unique()
print(F)

['Abu_Dhabi' 'Dubai' 'Sharjah']

G=df['avg_temperature'].unique()
print(G)

[30 33 34 29 28 31 20 27 26]

I =df['best_bowler'].unique()
print(I)

['Josh_Hazlewood' 'Adil_Rashid' 'Shakib_al_Hassan' 'Shaheen_shah'
 'Mujeeb_ur_Rehman' 'Dwaine_Pretorious' 'Haris_Rauf' 'Tymal_Mills'
 'Ruben_Trumpelmann' 'Adam_Zampa' 'Shoriful_Islam' 'Imad_Wasim'
 'Tabraiz_Shamsi' 'Criss_Jordan' 'Hamid_Hassan' 'Trent_Boult'
 'Wanindu_Hasaranga' 'Anrich_Nortje' 'Imad_wasim' 'Safyaan_Sharif'
 'Mohammed Shami' 'Tim_Southee' 'Ravindra_Jadeja' 'Kagiso_Rabada'
 'Shadab_Khan' 'Liam_Livingstone']

H =df['bowling_arm'].unique()
print(H)

['Right' 'Left']

J =df['bowling_style'].unique()
print(J)

['Pacer' 'Leg_spin' 'Off_spin' 'Orthodox' 'Unorthodox']

K =df['most_individual_wickets'].unique()
print(K)

[2 4 3 5 1]

H =df['best_batter_team'].unique()
print(H)

['SouthAfrica' 'England' 'Srilanka' 'Pakistan' 'Afghanistan' 'Windies'
 'ScotLand' 'Australia' 'Bangladesh' 'New_Zealand' 'India']

I =df['Player_of_the_match'].unique()
print(I)

['Josh_Hazlewood' 'Moeen_Ali' 'Charith_Asalanka' 'Shaheen_shah'
 'Mujeeb_ur_Rehman' 'Anrich_Nortje' 'Haris_Rauf' 'Jason_Roy'
 'Ruben_Trumpelmann' 'Adam_Zampa' 'Nicholas_Pooran' 'Asif_Ali'
 'Tabraiz_Shamsi' 'Chris_Jordan' 'Naveen_ul_Haq' 'Trent_Boult'
 'Jos_Buttler' 'Kagiso_Rabada' 'Muhammad_Rizwan' 'Martin_Guptill'
 'Rohit_Sharma' 'Chrith_Adalanka' 'James_Neesham' 'Ravindra_Jadeja'
 'David_Warner' 'Rassie_van_der_Dussen' 'Shoaib_Malik' 'Daryl_Mitchell'
 'Matthew_Wade' 'Mitchell_Marsh']

#remnaming
df = df.rename(columns = {'Unnamed: 0' : 'Match Number'})
df.head()

	Match Number	team_1	team_2	stage	Winner_toss	Toss_descision	time	venue	avg_temperature	best_bowler	...	best_bowler_country	best_batter	batting_hand	high_indvidual_scores	strike_rate	best_batter_team	target	target_achieved	Player_of_the_match	Winner
0	Match_1	Australia	SouthAfrica	Group_stage	Australia	Fielding	afternoon	Abu_Dhabi	30	Josh_Hazlewood	...	Australia	Aiden_Markram	Right	40	111.10	SouthAfrica	119	1	Josh_Hazlewood	Australia
1	Match_2	England	Windies	Group_stage	England	Fielding	evening	Dubai	33	Adil_Rashid	...	England	Jos_Buttler	Right	24	109.10	England	56	1	Moeen_Ali	England
2	Match_3	Srilanka	Bangladesh	Group_stage	Srilanka	Fielding	afternoon	Sharjah	34	Shakib_al_Hassan	...	Bangladesh	Charith_Asalanka	Left	80	163.20	Srilanka	172	1	Charith_Asalanka	Srilanka
3	Match_4	Pakistan	India	Group_stage	Pakistan	Fielding	evening	Dubai	34	Shaheen_shah	...	Pakistan	Muhammad_Rizwan	Right	79	143.60	Pakistan	152	1	Shaheen_shah	Pakistan
4	Match_5	Afghanistan	Scotland	Group_stage	Afghanistan	Batting	evening	Sharjah	33	Mujeeb_ur_Rehman	...	Afghanistan	Najibullah_Zadran	Left	59	173.53	Afghanistan	191	0	Mujeeb_ur_Rehman	Afghanistan

5 rows × 24 columns

#index match
df = df.set_index('Match Number')
df.head()

	team_1	team_2	stage	Winner_toss	Toss_descision	time	venue	avg_temperature	best_bowler	bowling_arm	...	best_bowler_country	best_batter	batting_hand	high_indvidual_scores	strike_rate	best_batter_team	target	target_achieved	Player_of_the_match	Winner
Match Number
Match_1	Australia	SouthAfrica	Group_stage	Australia	Fielding	afternoon	Abu_Dhabi	30	Josh_Hazlewood	Right	...	Australia	Aiden_Markram	Right	40	111.10	SouthAfrica	119	1	Josh_Hazlewood	Australia
Match_2	England	Windies	Group_stage	England	Fielding	evening	Dubai	33	Adil_Rashid	Right	...	England	Jos_Buttler	Right	24	109.10	England	56	1	Moeen_Ali	England
Match_3	Srilanka	Bangladesh	Group_stage	Srilanka	Fielding	afternoon	Sharjah	34	Shakib_al_Hassan	Left	...	Bangladesh	Charith_Asalanka	Left	80	163.20	Srilanka	172	1	Charith_Asalanka	Srilanka
Match_4	Pakistan	India	Group_stage	Pakistan	Fielding	evening	Dubai	34	Shaheen_shah	Left	...	Pakistan	Muhammad_Rizwan	Right	79	143.60	Pakistan	152	1	Shaheen_shah	Pakistan
Match_5	Afghanistan	Scotland	Group_stage	Afghanistan	Batting	evening	Sharjah	33	Mujeeb_ur_Rehman	Right	...	Afghanistan	Najibullah_Zadran	Left	59	173.53	Afghanistan	191	0	Mujeeb_ur_Rehman	Afghanistan

5 rows × 23 columns

Time =df['time'].value_counts()

Time

evening      20
afternoon    13
Name: time, dtype: int64

type(Time)

pandas.core.series.Series

toss_list =df['Winner_toss'].tolist()
win_list=df['Winner'].tolist()
winner=0
looser=0
for i in range(len(toss_list)):
    if(toss_list[i] == win_list[i]):
        winner +=1
    else:
        looser +=1
        
        
print("Won Toss and Won Match:",winner)
print("Won Toss and Loose Match:",looser)

Won Toss and Won Match: 24
Won Toss and Loose Match: 9

#match won by each team
plt.figure(figsize = (8,6))
sns.countplot(df['time'], palette = 'Set1')
plt.title("Time Slot :Match")
plt.show()

# Temprature range:
fig =px.pie(Time ,values =df['avg_temperature'].value_counts(),names=['30-Temp','33-Temp','34-Temp','29-Temp',
                                                                      '28-Temp','31-Temp','20-Temp','27-temp','26-Temp'],
            title=' Temparature Range Records while Match:')
fig.update_traces(textposition='inside', textinfo='percent+label')
fig.show()
#temp in *c

#match won by each team
sns.countplot(y='Winner',data=df)

<AxesSubplot:xlabel='count', ylabel='Winner'>

#count of venue
plt.figure(figsize = (8,6))
sns.countplot(df['venue'], palette = 'Set1')
plt.title("Venue for Tournament")
plt.show()

#Man of MATCH
print("Player : No_of_times_player_of_match")
df['Player_of_the_match'].value_counts().nlargest(5)

Player : No_of_times_player_of_match

Ravindra_Jadeja    2
Adam_Zampa         2
Trent_Boult        2
Kagiso_Rabada      1
Muhammad_Rizwan    1
Name: Player_of_the_match, dtype: int64

# correlation
plt.figure(figsize = (8,6))
sns.heatmap(df.corr(), annot = True, cmap = 'OrRd')
plt.title("Correlation")
plt.show()

#colum name-update
df.target_achieved[df['target_achieved'] == 0] = 'Achieved'
df.target_achieved[df['target_achieved'] == 1] = 'Not Achieved'
df.head()

	team_1	team_2	stage	Winner_toss	Toss_descision	time	venue	avg_temperature	best_bowler	bowling_arm	...	best_bowler_country	best_batter	batting_hand	high_indvidual_scores	strike_rate	best_batter_team	target	target_achieved	Player_of_the_match	Winner
Match Number
Match_1	Australia	SouthAfrica	Group_stage	Australia	Fielding	afternoon	Abu_Dhabi	30	Josh_Hazlewood	Right	...	Australia	Aiden_Markram	Right	40	111.10	SouthAfrica	119	Not Achieved	Josh_Hazlewood	Australia
Match_2	England	Windies	Group_stage	England	Fielding	evening	Dubai	33	Adil_Rashid	Right	...	England	Jos_Buttler	Right	24	109.10	England	56	Not Achieved	Moeen_Ali	England
Match_3	Srilanka	Bangladesh	Group_stage	Srilanka	Fielding	afternoon	Sharjah	34	Shakib_al_Hassan	Left	...	Bangladesh	Charith_Asalanka	Left	80	163.20	Srilanka	172	Not Achieved	Charith_Asalanka	Srilanka
Match_4	Pakistan	India	Group_stage	Pakistan	Fielding	evening	Dubai	34	Shaheen_shah	Left	...	Pakistan	Muhammad_Rizwan	Right	79	143.60	Pakistan	152	Not Achieved	Shaheen_shah	Pakistan
Match_5	Afghanistan	Scotland	Group_stage	Afghanistan	Batting	evening	Sharjah	33	Mujeeb_ur_Rehman	Right	...	Afghanistan	Najibullah_Zadran	Left	59	173.53	Afghanistan	191	Achieved	Mujeeb_ur_Rehman	Afghanistan

5 rows × 23 columns

plt.figure(figsize = (8,6))
sns.countplot(df['stage'], palette = 'Set1')
plt.title("Stage of Tournament")
plt.show()

plt.figure(figsize = (8,6))
sns.countplot(y=df['best_batter_team'], palette = 'Set1')
plt.title("Best Batting Team")
plt.show()

plt.figure(figsize = (8,6))
sns.countplot(y=df['best_bowler_country'], palette = 'Set1')
plt.title("Best Bolwing Team")
plt.show()

print("Top 5 Batsman in T20-World-Cup-2021:")
df['best_batter'].value_counts().nlargest(5)

Top 5 Batsman in T20-World-Cup-2021:

Muhammad_Rizwan      4
Jos_Buttler          3
Daryl_Mitchell       2
David_Warner         2
Najibullah_Zadran    2
Name: best_batter, dtype: int64

print("Top 5 Bolwer in T20-World-Cup-2021:")
df['best_bowler'].value_counts().nlargest(5)

Top 5 Bolwer in T20-World-Cup-2021:

Josh_Hazlewood       3
Trent_Boult          2
Ravindra_Jadeja      2
Shadab_Khan          2
Wanindu_Hasaranga    2
Name: best_bowler, dtype: int64

print("Top 10 highest Score:")
df['target'].sort_values(ascending=False).nlargest(10)

Top 10 highest Score:

Match Number
Match_21    211
Match_5     191
Match_19    190
Match_29    190
Match_27    190
Match_23    190
Match_32    177
Match_33    173
Match_20    173
Match_3     172
Name: target, dtype: int64

print("Least 10  Score:")
df['target'].sort_values(ascending=False).nsmallest(10)

Least 10  Score:

Match Number
Match_2      56
Match_22     74
Match_18     85
Match_25     86
Match_9     110
Match_16    111
Match_1     119
Match_8     125
Match_28    125
Match_14    126
Name: target, dtype: int64

print("Top 10 high_indvidual_scores:")
df['high_indvidual_scores'].sort_values(ascending=False).nlargest(10)

Top 10 high_indvidual_scores:

Match Number
Match_17    101
Match_27     94
Match_20     93
Match_26     89
Match_33     85
Match_23     81
Match_3      80
Match_4      79
Match_19     79
Match_21     74
Name: high_indvidual_scores, dtype: int64

#by each team
plt.figure(figsize = (8,6))
sns.countplot(df['Toss_descision'], palette = 'Set1')
plt.title("Toss descision")
plt.show()

#team 1 & target achievement
achieved_target_team1 = df.groupby(['team_1', 'target_achieved']).size().reset_index(name = 'Count')

#visualize team 1
plt.figure(figsize = (10,6))
chart = sns.barplot(data =achieved_target_team1 , x = 'team_1', y ='Count', hue = 'target_achieved', palette = 'Set1')
chart.set_xticklabels(chart.get_xticklabels(), rotation = 35)
plt.title("Team 1 - Achievement")
plt.show()

#team 2 & target achievement
achieved_target_team2 = df.groupby(['team_2', 'target_achieved']).size().reset_index(name = 'Count')

#visualize team 2
plt.figure(figsize = (10,6))
chart = sns.barplot(data =achieved_target_team2 , x = 'team_2', y ='Count', hue = 'target_achieved', palette = 'Set1')
chart.set_xticklabels(chart.get_xticklabels(), rotation = 35)
plt.title("Team 2 - Achievement")
plt.show()

Team =df.groupby(['team_1','team_2','Winner_toss','time','Toss_descision','venue','Player_of_the_match']).size()

Team=Team.to_frame()

Team

							0
team_1	team_2	Winner_toss	time	Toss_descision	venue	Player_of_the_match
Afghanistan	Namibia	Afghanistan	afternoon	Batting	Abu_Dhabi	Naveen_ul_Haq	1
	Scotland	Afghanistan	evening	Batting	Sharjah	Mujeeb_ur_Rehman	1
Australia	Bangladesh	Australia	afternoon	Fielding	Dubai	Adam_Zampa	1
	New_Zealand	Australia	evening	Fielding	Dubai	Mitchell_Marsh	1
	Pakistan	Australia	evening	Fielding	Dubai	Matthew_Wade	1
	SouthAfrica	Australia	afternoon	Fielding	Abu_Dhabi	Josh_Hazlewood	1
	Srilanka	Australia	evening	Fielding	Dubai	Adam_Zampa	1
	Windies	Australia	afternoon	Fielding	Abu_Dhabi	David_Warner	1
England	Australia	England	evening	Fielding	Dubai	Chris_Jordan	1
	Bangladesh	Bangladesh	afternoon	Batting	Abu_Dhabi	Jason_Roy	1
	Srilanka	Srilanka	evening	Fielding	Sharjah	Jos_Buttler	1
	Windies	England	evening	Fielding	Dubai	Moeen_Ali	1
India	Afghanistan	Afghanistan	evening	Fielding	Abu_Dhabi	Rohit_Sharma	1
	Namibia	India	evening	Fielding	Dubai	Ravindra_Jadeja	1
	ScotLand	India	evening	Fielding	Dubai	Ravindra_Jadeja	1
Namibia	ScotLand	Namibia	evening	Fielding	Abu_Dhabi	Ruben_Trumpelmann	1
New_Zealand	Afghanistan	Afghanistan	afternoon	Batting	Abu_Dhabi	Trent_Boult	1
	England	New_Zealand	evening	Fielding	Abu_Dhabi	Daryl_Mitchell	1
	India	New_Zealand	evening	Fielding	Dubai	Trent_Boult	1
	Namibia	Namibia	afternoon	Fielding	Sharjah	James_Neesham	1
	ScotLand	New_Zealand	afternoon	Fielding	Dubai	Martin_Guptill	1
Pakistan	Afghanistan	Afghanistan	evening	Batting	Dubai	Asif_Ali	1
	India	Pakistan	evening	Fielding	Dubai	Shaheen_shah	1
	Namibia	Pakistan	evening	Batting	Abu_Dhabi	Muhammad_Rizwan	1
	New_Zealand	Pakistan	evening	Fielding	Sharjah	Haris_Rauf	1
	ScotLand	Pakistan	evening	Batting	Sharjah	Shoaib_Malik	1
SouthAfrica	Bangladesh	SouthAfrica	afternoon	Fielding	Abu_Dhabi	Kagiso_Rabada	1
	England	England	evening	Fielding	Sharjah	Rassie_van_der_Dussen	1
	Srilanka	SouthAfrica	afternoon	Fielding	Sharjah	Tabraiz_Shamsi	1
	Windies	SouthAfrica	afternoon	Fielding	Dubai	Anrich_Nortje	1
Srilanka	Bangladesh	Srilanka	afternoon	Fielding	Sharjah	Charith_Asalanka	1
	Windies	Windies	evening	Fielding	Abu_Dhabi	Chrith_Adalanka	1
Windies	Bangladesh	Bangladesh	afternoon	Fielding	Sharjah	Nicholas_Pooran	1

type(Team)

pandas.core.frame.DataFrame

fig = px.sunburst(df, names=None, values=None, parents=None, path=['team_1','team_2','Toss_descision','Winner','venue'], 
                   color='team_2', color_continuous_scale=None, range_color=None, color_continuous_midpoint=None, 
                  color_discrete_sequence=None, color_discrete_map={},
                  hover_data=['team_1','team_2','Toss_descision','Winner','venue'],
                 labels={}, title= "Team VS Team - Winner")
fig.show()

Stage=df.groupby(['stage','team_1','team_2','Winner_toss','time','Toss_descision','venue']).size()

Stage=Stage.to_frame()

Stage

							0
stage	team_1	team_2	Winner_toss	time	Toss_descision	venue
Final	Australia	New_Zealand	Australia	evening	Fielding	Dubai	1
Group_stage	Afghanistan	Namibia	Afghanistan	afternoon	Batting	Abu_Dhabi	1
		Scotland	Afghanistan	evening	Batting	Sharjah	1
	Australia	Bangladesh	Australia	afternoon	Fielding	Dubai	1
		SouthAfrica	Australia	afternoon	Fielding	Abu_Dhabi	1
		Srilanka	Australia	evening	Fielding	Dubai	1
		Windies	Australia	afternoon	Fielding	Abu_Dhabi	1
	England	Australia	England	evening	Fielding	Dubai	1
		Bangladesh	Bangladesh	afternoon	Batting	Abu_Dhabi	1
		Srilanka	Srilanka	evening	Fielding	Sharjah	1
		Windies	England	evening	Fielding	Dubai	1
	India	Afghanistan	Afghanistan	evening	Fielding	Abu_Dhabi	1
		Namibia	India	evening	Fielding	Dubai	1
		ScotLand	India	evening	Fielding	Dubai	1
	Namibia	ScotLand	Namibia	evening	Fielding	Abu_Dhabi	1
	New_Zealand	Afghanistan	Afghanistan	afternoon	Batting	Abu_Dhabi	1
		India	New_Zealand	evening	Fielding	Dubai	1
		Namibia	Namibia	afternoon	Fielding	Sharjah	1
		ScotLand	New_Zealand	afternoon	Fielding	Dubai	1
	Pakistan	Afghanistan	Afghanistan	evening	Batting	Dubai	1
		India	Pakistan	evening	Fielding	Dubai	1
		Namibia	Pakistan	evening	Batting	Abu_Dhabi	1
		New_Zealand	Pakistan	evening	Fielding	Sharjah	1
		ScotLand	Pakistan	evening	Batting	Sharjah	1
	SouthAfrica	Bangladesh	SouthAfrica	afternoon	Fielding	Abu_Dhabi	1
		England	England	evening	Fielding	Sharjah	1
		Srilanka	SouthAfrica	afternoon	Fielding	Sharjah	1
		Windies	SouthAfrica	afternoon	Fielding	Dubai	1
	Srilanka	Bangladesh	Srilanka	afternoon	Fielding	Sharjah	1
		Windies	Windies	evening	Fielding	Abu_Dhabi	1
	Windies	Bangladesh	Bangladesh	afternoon	Fielding	Sharjah	1
Semi_Final	Australia	Pakistan	Australia	evening	Fielding	Dubai	1
	New_Zealand	England	New_Zealand	evening	Fielding	Abu_Dhabi	1

fig = px.sunburst(df, names=None, values=None, parents=None, path=['stage','team_1','team_2','Winner_toss','time','Toss_descision','venue'], 
                   color='team_1', color_continuous_scale=None, range_color=None, color_continuous_midpoint=None, 
                  color_discrete_sequence=None, color_discrete_map={},
                  hover_data=['stage','team_1','team_2','time','Toss_descision','venue'] ,
                 labels={'Stage','Team-A','Team-B','Time','Toss_descision','Venue'}, title= "Detailed_Analysis Chart")
fig.show()

#
sns.pairplot(df,hue='team_1')

<seaborn.axisgrid.PairGrid at 0x1faf3567ac0>

-----------------XXX-----------------
@copyright : Saurabh 29-nov